Inference techniques either move a deployment along the latency–throughput frontier or push the entire frontier out, creating more efficiency to allocate.
This is a tautology. You can say that with anything. Gastronomy techniques will make a previous recipe better, or create a new recipe better than others, or a mix of both.
The author does not deeply mention that quality/intelligence is a third dimension here in addition to throughput and latency, and the frontier is jagged so quality and intelligence require bespoke benchmarks to evaluate tradeoffs for speed and cost.
These are both good points that I attempted to cover, quotes:
> In practice, the efficient frontier is very jagged. Rather than a smooth, continuous line between outcomes, small changes can have big impacts. These cutoff points are often unintuitive and must be discovered empirically through sweeps.
> However, quantization introduces a new set of tradeoffs between quality and serving efficiency. This is a particularly jagged frontier, where a large degree of improvement to serving efficiency is possible with little-to-no reduction in model quality, especially when using microscaling floating-point number formats like MXFP4 and NVFP4.
Would appreciate ideas on how to explain in greater depth
this is a nice and concise writeup. what's striking to me is that these techniques really have not changed in /years/. sure, precision has become slightly lower, spec decoding acceptance has gotten slightly better and the complexity of parallelism is trickier with mixture of experts. but no new concepts in a very long time!
the absolute most impactful improvements for inference comes at architecture design time. I firmly believe everyone who cares about impacting model efficiency should look there
> In practice, the efficient frontier is very jagged. Rather than a smooth, continuous line between outcomes, small changes can have big impacts. These cutoff points are often unintuitive and must be discovered empirically through sweeps.
> However, quantization introduces a new set of tradeoffs between quality and serving efficiency. This is a particularly jagged frontier, where a large degree of improvement to serving efficiency is possible with little-to-no reduction in model quality, especially when using microscaling floating-point number formats like MXFP4 and NVFP4.
Would appreciate ideas on how to explain in greater depth
the absolute most impactful improvements for inference comes at architecture design time. I firmly believe everyone who cares about impacting model efficiency should look there
But overall yes the fundamentals of LLM performance optimization have been remarkably stable over the last few years.